Rohan's Bytes
Subscribe
Sign in
Home
Notes
Chat
ML Interview Series
AI Tutorial
Daily AI Newsletter
AI Paper Explained
ML Case-Study π
Probability-Interview-Series
Archive
About
π OpenAI's Realtime API with WebRTC
Use WebRTC to connect client-side applications to the Realtime API.
Dec 18, 2024
Β
β’
Β
Rohan Paul
17
1
π DeepSeek-R1 fails every safety test thrown at it and failed to block any harmful request
DeepSeek-R1 fails every safety test, ByteDance's OmniHuman-1 stuns with lifelike videos, DeepMind proves RL beats fine-tuning, OpenAI eyes smartphoneβ¦
Feb 4, 2025
14
1
ποΈ OpenAI launches GPT-5.4 with Pro and Thinking versions
With GPT-5.4 hitting a βhighβ cyber threat rating and FrontierMath records, the Pentagon labeling Anthropic a supply chain risk, new data center growthβ¦
Mar 7
11
3
Most Popular
View all
ππ GPT-5 casually generated completely new mathematics.
Aug 21, 2025
3
1
π‘ AI is not exactly creating β10x workerβ
Aug 22, 2025
11
3
1
π‘ Model Context Protocol (MCP) 101
Mar 7, 2025
27
1
π Google DeepMind debuted Genie 3 and it is literally βout of this worldβ
Jan 31
6
π§ Anthropic's 212-page system card for its latest Claude Opus 4.6 has many interesting stuff
Feb 6
13
1
1
π§ DeepSeek just improved the Transformer architecture
Jan 2
13
2
Daily AI Newsletter
View all
ποΈ OpenAI launches GPT-5.4 with Pro and Thinking versions
With GPT-5.4 hitting a βhighβ cyber threat rating and FrontierMath records, the Pentagon labeling Anthropic a supply chain risk, new data center growthβ¦
Mar 7
11
3
ποΈ Anthropic has made its Claude Memory feature free for everyone
Gemini 3.1 Lite launches for devs, GPT-5.3 Instant ditches the preachiness, AI aids Fields Medal math breakthrough, Codex hits Windows native, and theβ¦
Mar 6
10
1
A third era is now emerging, driven by AI agents capable of tackling large tasks independently over extended periods.
Claudeβs 81K star repo & voice mode, GPT-5.4 leaks, and OpenAIβs War Dept tie-up. Plus: AgentConductorβs code gen, Qwen 3.5 on iPhone, and Alibabaβ¦
Mar 4
11
2
ποΈ Alibaba released their open-source Qwen3.5-9B model, and it holds its own against OpenAI's 120B param gpt-oss system.
Anthropic sues gov, DeepSeek V4 nears, and LLM privacy decoded. Plus: Altman on OpenAIβs Pentagon deal, a massive Video Reasoning suite, and SWE-1.6βsβ¦
Mar 3
8
1
ποΈ OpenAI sweeps in to ink deal with Pentagon as Anthropic is designated a βsupply chain riskβ
AI Selves go mainstream as agent reliability comes under scrutiny, 93% of U.S. jobs face AI exposure, OpenAI lands a historic $110B round, and Anthropicβ¦
Feb 28
7
1
Ex-Twitter CEOβs firm Block to replace almost 50% workforce with AI
AI crosses new thresholds: Martian launches its massive coding benchmark, Google advances image creation with Nano Banana 2, and Anthropic makes aβ¦
Feb 28
6
1
ποΈ Perplexity just dropped Computer, a new system that handles complete workflows from start to finish.
Anthropic upgrades Cowork for seamless cross-app finance and launches Remote Control for mobile coding. Plus, Andrej Karpathy drops a must-read newβ¦
Feb 26
5
ποΈ IBM stock dipped more than 13% once Anthropic released a blog saying Claude can optimize legacy COBOL code
Enterprise AI hits the last mile, Pentagon probes military models, a 2028 intelligence crisis blog goes viral, predicting massive job-loss, and OpenAIβ¦
Feb 25
10
2
ποΈ Anthropic launched Claude Code Security to scan your code repositories for bugs and suggest security patches.
From X-Humanoidβs robot platform to claims of massive AI bot attacks, 84% of people still haven't used AI, DeepMindβs new framework for tasking agentsβ¦
Feb 23
11
1
Claude Code on desktop can now preview your running apps, review your code & handle CI failures, PRs in background
New Paper says prompt repetition boosts non-reasoning LLMs, Taalas drops a high-throughput inference chip, Wolf reframes AIβs impact, NanoClaw hitsβ¦
Feb 21
8
π Google has taken the AI lead again with Gemini 3.1 Pro.
Lyria 3 generates music in-Gemini, new CEO survey exposes AIβs productivity paradox, Microsoft advances durable data-center storage, and researchersβ¦
Feb 19
5
ποΈ OpenAI teamed up with crypto firm Paradigm to launch EVMBench to test AI agents on smart contract security
Nvidia-Meta multimillion AI chip deal, AGIBOT A3 robotics demo, Andrew Yang office thesis, Figma Claude Code to Canvas integration.
Feb 18
8
2
AI Tutorial
View all
Vector Index Methods for Document Digitization in LLM Applications
Browse all previously published AI Tutorials here.
Jun 16, 2025
1
Document digitization and chunking strategies for finding similar customer reviews using semantic similarity
Browse all previously published AI Tutorials here.
Jun 16, 2025
vector search strategies, focusing on clustering and Locality-Sensitive Hashing (LSH) in the context of document digitization and chunking
Browse all previously published AI Tutorials here.
Jun 16, 2025
Random Projection Index (RPI) for Document Digitization in LLM Pipelines 2024-2025 Review
Browse all previously published AI Tutorials here.
Jun 16, 2025
Product quantization PQ indexing method
Browse all previously published AI Tutorials here.
Jun 16, 2025
Locality-Sensitive Hashing in Document Retrieval and LLM Chunking A 2024-2025 Review
Browse all previously published AI Tutorials here.
Jun 16, 2025
How would you decide ideal search similarity metrics for the use case
Browse all previously published AI Tutorials here.
Jun 16, 2025
Vector Databases for RAG Literature Review
Browse all previously published AI Tutorials here.
Jun 16, 2025
Clustering techniques used in document digitization and chunking for LLMs, focusing on their role in reducing search space
Browse all previously published AI Tutorials here.
Jun 16, 2025
Vector Databases vs. Traditional Databases for LLM Document Retrieval
Browse all previously published AI Tutorials here.
Jun 16, 2025
Vector Databases in Document Retrieval and RAG Applications
Browse all previously published AI Tutorials here.
Jun 16, 2025
Challenges and techniques of filtering in vector databases for document digitization and chunking in LLMs
Browse all previously published AI Tutorials here.
Jun 16, 2025
This site requires JavaScript to run correctly. Please
turn on JavaScript
or unblock scripts